Benchmarks · composite
Arena Text · Industry: entertainment, sports and media
Crowdsourced pairwise human preference on open-ended text prompts (style control on); Bradley-Terry rating. Only the Industry: entertainment, sports and media category.
211 models · 222 results · updated 2026-11-09 · arena.ai ↗
Leaderboard
Gemini 4 Argon high
All results
222 rows| # | Model | Effort | Score |
|---|---|---|---|
| 1 | Gemini 4 Argon | high | 1516 ±10 |
| 2 | Gemini 4 Carbon | high | 1509 ±19 |
| 3 | Opus 5.5 | high | 1497 ±11 |
| 4 | Fable 5 | high | 1495 ±7 |
| 5 | Opus 4.6 | high | 1491 ±6 |
| 6 | Muse Wonder | max | 1490 ±12 |
| 7 | Opus 4.7 | high | 1481 ±6 |
| 8 | Gemini 3.8 Flash | high | 1480 ±6 |
| 9 | Kimi K3.1 | max | 1479 ±21 |
| 10 | Fable 5.1 | max | 1479 ±9 |
| 11 | Opus 4.6 | max | 1476 ±5 |
| 12 | Gemini 3.7 Flash | high | 1475 ±8 |
| 13 | Opus 4.7 | max | 1472 ±6 |
| 14 | GPT-5.6 Sol | xhigh | 1470 ±7 |
| 15 | Gemini 3.1 Pro | high | 1470 ±5 |
| 16 | Gemini 3 Pro | high | 1469 ±7 |
| 17 | Muse Spark 1.3 | max | 1466 ±8 |
| 18 | Qwen 3.8 Max | max | 1464 ±7 |
| 19 | Opus 5 | high | 1463 ±6 |
| 20 | Muse Spark | 1463 ±12 | |
| 21 | Opus 5 | max | 1462 ±7 |
| 22 | Gemini 3.6 Flash | high | 1461 ±7 |
| 23 | Opus 4.8 | high | 1461 ±6 |
| 24 | Kimi K3 | max | 1458 ±7 |
| 25 | Gemini 3.5 Flash | medium | 1457 ±7 |
| 26 | Opus 4.5 | high | 1456 ±8 |
| 27 | GPT-6 Astra | max | 1456 ±10 |
| 28 | Opus 4.8 | max | 1455 ±6 |
| 29 | Gemini 3.5 Flash | high | 1455 ±7 |
| 30 | Sonnet 5.5 | xhigh | 1455 ±11 |